Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15351
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to data structures, specifically keys and values in maps or dictionaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraReports
    -0.68
    WindowConstants
    -0.62
    makeText
    -0.57
    AppendLine
    -0.56
    ++];
    -0.55
    част
    -0.54
     זה
    -0.54
    softc
    -0.53
     insuffisamment
    -0.53
    ovací
    -0.53
    POSITIVE LOGITS
    InjectAttribute
    0.74
     propOrder
    0.74
    ьаж
    0.64
    ]")]
    0.59
    entrySet
    0.58
    ForValue
    0.57
     keys
    0.57
    AddHtmlAttribute
    0.56
    transQ
    0.56
    keySet
    0.55
    Activations Density 0.177%

    No Known Activations